Blind Suppression of Nonstationary Diffuse Acoustic Noise Based on Spatial Covariance Matrix Decomposition

We propose methods for blind suppression of nonstationary diffuse noise based on decomposition of the observed spatial covariance matrix into signal and noise parts. In modeling noise to regularize the ill-posed decomposition problem, we exploit spatial invariance (isotropy) instead of temporal inva...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Signal Processing Systems Jg. 79; H. 2; S. 145 - 157
Hauptverfasser: Ito, Nobutaka, Vincent, Emmanuel, Nakatani, Tomohiro, Ono, Nobutaka, Araki, Shoko, Sagayama, Shigeki
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Boston Springer Science and Business Media LLC 01.05.2015
Springer US
Schlagworte:
[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing
[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Circuits and Systems
Computer Imaging
Diffuse noise
Electrical Engineering
Engineering
Image Processing and Computer Vision
Least squares estimation
Maximum likelihood estimation
Noise suppression
Pattern Recognition
Pattern Recognition and Graphics
Signal,Image and Speech Processing
Spatial covariance matrix
Vision
Diffuse noise
Maximum likelihood estimation
Spatial covariance matrix
Least squares estimation
Noise suppression
ISSN:1939-8018, 1939-8115
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose methods for blind suppression of nonstationary diffuse noise based on decomposition of the observed spatial covariance matrix into signal and noise parts. In modeling noise to regularize the ill-posed decomposition problem, we exploit spatial invariance (isotropy) instead of temporal invariance (stationarity). The isotropy assumption is that the spatial cross-spectrum of noise is dependent on the distance between microphones and independent of the direction between them. We propose methods for spatial covariance matrix decomposition based on least squares and maximum likelihood estimation. The methods are validated on real-world data.
ISSN:1939-8018
1939-8115
DOI:10.1007/s11265-014-0922-z